Automatic detection of unstained viable cells in bright field images using a support vector machine with an improved training procedure

Long, Xi; Cleveland, Louis; Yao, Yan

doi:10.1016/j.compbiomed.2004.12.002

Cited by 34 publications

(18 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each class i is encoded by the ith row of the matrix C. This codeword is denoted by C i . To classify a new instance x, the vector formed by the output of the classifiers F(x) = (f 1 (x),f 2 (2) . .…”

Section: Brief Summary Of Ecocmentioning

confidence: 99%

“…In this method, pixel patches from the original images are mapped to ''confidence values'' that reflect the estimated class probability. Patches containing centered cells give the highest probability and thereby provide the localization (see Section 3 for more details) [1,2]. Here, we develop a new ECOC-based probability estimation algorithm to enable the pixel patch decomposition technique to be used for both multiclass classification and localization in images.…”

Section: Introductionmentioning

confidence: 99%

“…This has recently become possible for bright field images of unstained cells in cultures using statistical learning techniques [1]. Even the distinction between viable and non-viable cells in these images can be done with sufficient accuracy for practical applications [2]. To proceed further towards the goal of fully automated microscopy, it is of critical importance to develop algorithms that can sort cell objects into subtypes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multiclass cell detection in bright field images of cell mixtures with ECOC probability estimation

Long

Cleveland

Yao

2008

Image and Vision Computing

Self Cite

View full text Add to dashboard Cite

Section: Brief Summary Of Ecocmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multiclass cell detection in bright field images of cell mixtures with ECOC probability estimation

Long

Cleveland

Yao

2008

Image and Vision Computing

Self Cite

View full text Add to dashboard Cite

“…A fixed-size square patch is sampled at each pixel and used to train a cell-background classifier. The features can be either the patches themselves as in [1] or the patches after applying traditional feature extraction schemes as in [2], [3], [4].…”

Section: Introductionmentioning

confidence: 99%

Using the Monogenic Signal for Cell-Background Classification in Bright-Field Microscope Images

Mualla

Scholl

Sommerfeldt

et al. 2013

Bildverarbeitung Für Die Medizin 2013

View full text Add to dashboard Cite

Abstract. Some cell detection approaches which deal with bright-field microscope images utilize defocussing to increase the image contrast. The latter is related to the physical light phase through the transport of intensity equation (TIE). Recently, it was shown that it is possible to approximate the solution of the TIE using a modified monogenic signal framework. We show empirically that using the local phase of the previous monogenic signal in place of the defocused image improves the cellbackground classification rate. The evaluation was performed on L929 adherent cell line with more than 1000 manually labeled cells. The improvement was 6.8% using a random forest classifier and 10% using a support vector machine classifier with a radial basis function kernel.

show abstract

“…[10][11][12][13][14] However, most of these studies used manually acquired, high-resolution images, making it possible to extract rich, detailed quantitative information from the images for accurate classification. Furthermore, some image quantification parameters proposed in these studies are computationally expensive and cannot be calculated with off-the-shelf imageprocessing software.…”

mentioning

confidence: 99%

A Support Vector Machine Classifier for Recognizing Mitotic Subphases Using High-Content Screening Data

Tao¹,

Hoyt²,

Yan³

2007

SLAS Discovery

View full text Add to dashboard Cite

High-content screening studies of mitotic checkpoints are important for identifying cancer targets and developing novel cancerspecific therapies. A crucial step in such a study is to determine the stage of cell cycle. Due to the overwhelming number of cells assayed in a high-content screening experiment and the multiple factors that need to be taken into consideration for accurate determination of mitotic subphases, an automated classifier is necessary. In this article, the authors describe in detail a support vector machine (SVM) classifier that they have implemented to recognize various mitotic subphases. In contrast to previous studies to recognize subcellular patterns, they used only low-resolution cell images and a few parameters that can be calculated inexpensively with off-the-shelf image-processing software. The performance of the SVM was evaluated with a cross-validation method and was shown to be comparable to that of a human expert. (Journal of Biomolecular Screening 2007:490-496)

show abstract

Automatic detection of unstained viable cells in bright field images using a support vector machine with an improved training procedure

Cited by 34 publications

References 11 publications

Multiclass cell detection in bright field images of cell mixtures with ECOC probability estimation

Multiclass cell detection in bright field images of cell mixtures with ECOC probability estimation

Using the Monogenic Signal for Cell-Background Classification in Bright-Field Microscope Images

A Support Vector Machine Classifier for Recognizing Mitotic Subphases Using High-Content Screening Data

Contact Info

Product

Resources

About